devtools-testing-guidance

Guidance on selecting the appropriate test suite (Unit, API, or E2E tests) when writing new tests in Chrome DevTools. MUST be used when writing new tests.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/devtools-testing-guidance/SKILL.md

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-structured decision guide: lean bullets, concrete file locations, extensions, and BUILD.gn targets, with a clear default-first escalation logic and a clean boundary note toward devtools-verification. The only real defects are a garbled E2E BUILD.gn target name, mild API/E2E criteria overlap, and a redundant opening sentence.

Suggestions

Fix the E2E BUILD.gn line 'ts_e2e_library(ts_e2e_library)' — it reads as a typo; state the actual target name and where it applies.

Add a one-line tie-breaker for cases where both API and E2E criteria seem to apply (e.g., 'If the test needs the full DevTools UI, choose E2E; otherwise prefer API tests').

Delete the opening restatement of the frontmatter description and start directly at '## Choosing a Test Suite' to save tokens.

Dimension	Reasoning	Score
Conciseness	The body is lean — bullet lists of locations, extensions, and BUILD.gn targets with zero concept explanations — but the opening sentence ('This guide outlines when and how to select the appropriate test suite...') merely restates the frontmatter description and could be trimmed, matching anchor 4 rather than the every-token-earns-its-place anchor 5.	4 / 5
Actionability	Guidance is mostly executable and specific: co-location examples ('TimelinePanel.ts and TimelinePanel.test.ts'), file extensions ('.test.api.ts'), directory ('test/e2e/'), BUILD.gn targets, and the TestUniverse helper. It falls short of anchor 5 because the E2E BUILD.gn line reads 'ts_e2e_library(ts_e2e_library)' — a garbled target name — and no run commands are given (justifiably deferred to devtools-verification).	4 / 5
Workflow Clarity	The decision flow is clear: an explicit default ('The vast majority of tests in DevTools should be unit tests') followed by escalation criteria per suite, which for a simple selection skill approaches the unambiguous-single-action exception. It is not 5 because the API vs E2E criteria overlap ('complex setups' appears in both) without a crisp tie-breaker.	4 / 5
Progressive Disclosure	The body is under 50 lines, needs no external reference files (none exist in the bundle), and is organized into clean per-suite sections; the NOTE cleanly hands off execution concerns to the devtools-verification skill. Per the under-50-lines guideline, well-organized sections alone merit anchor 5.	5 / 5
	Total	17 / 20 Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A solid description with an explicit what and an explicit MUST-use trigger, well-targeted natural keywords, and a clear Chrome DevTools niche. Its main weaknesses are that it states only a single capability ("selecting") and its when-clause duplicates the what rather than broadening trigger coverage with synonyms.

Suggestions

Add one or two more concrete capability verbs beyond 'selecting' (e.g., 'Determines the correct test suite, file location, and BUILD.gn target for new DevTools tests').

Broaden the when-clause with natural trigger variations such as 'when adding unit, API, E2E, or end-to-end tests' or 'when deciding where a new test file belongs'.

Optionally distinguish the skill from the devtools-verification skill in the description itself (e.g., 'For how to run tests, see devtools-verification') to reduce overlap risk.

Dimension	Reasoning	Score
Specificity	The description names the domain ("selecting the appropriate test suite (Unit, API, or E2E tests)" in "Chrome DevTools") but the only concrete action stated is "selecting" — one capability, not the several specific actions anchor 4 requires; it is far more concrete than the generic anchor 2.	3 / 5
Completeness	Both what ("Guidance on selecting the appropriate test suite") and when ("MUST be used when writing new tests") are explicit, satisfying anchor 4; it is not anchor 5 because the when-clause largely restates the what rather than adding concrete, varied trigger phrases.	4 / 5
Trigger Term Quality	Natural phrases users would say are present ("writing new tests", "Unit, API, or E2E tests", "Chrome DevTools"), but common synonyms like "end-to-end" spelled out, "integration tests", or "test coverage" are missing, so it falls short of anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (test-suite selection in Chrome DevTools) with distinct triggers, but there is minor overlap risk with the sibling devtools-verification skill (how to run tests), which the body disambiguates but the description does not.	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ChromeDevTools/devtools-frontend
Path: .agents/skills/devtools-testing-guidance/SKILL.md
Commit: de3f9ca

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.